Trident: Efficient 4PC Framework for Privacy Preserving Machine Learningarxiv.org/pdf/1912.02631.pdf Abstract 本文提出环上遵循离线-在线范式的具有主动安全的四方隐私保护机器学习框架Trident, 可抵抗一个恶意敌手, 同时还实现了公平性(Fairness). 与三方的ABY3相比, 本文通过在离线阶段引入一个额外诚实方, 并...
CryptGPU: Fast Privacy-Preserving Machine Learning on the GPUarxiv.org/abs/2104.10949 Background & Motivation 目前大多数基于安全多方计算(MPC)的隐私保护机器学习方案都是运行在CPU上的,但是在明文机器学习领域GPU已经成为一项不可缺少的硬件设备。GPU强大的算力能够大大加快机器学习模型,尤其是神经网络的计算...
This is why we’re excited to share the work we’re doing as part of the Privacy Preserving Machine Learning (PPML) initiative. The PPML initiative was started in partnership between Microsoft Research and Microsoft product teams with the objective of protecting the confidentiality and pri...
New and efficient protocols are provided for privacy-preserving machine learning training (e.g., for linear regression, logistic regression and neural network using the stochastic gradient descent method). A protocols can use the two-server model, where data owners distribute their private data among...
不过,在 "联邦学习"(Federated Learning)设置中,服务器不需要访问任何单个用户的更新,就能执行随机梯度下降;它只需要得到随机用户子集的更新向量的元素加权平均值。使用安全聚合协议计算这些加权平均值将确保服务器只能了解到在这个随机选择的子集中有一个或多个用户写了一个给定的单词,而不能了解到是哪些用户。
1 介绍 本文是谷歌团队发在CCS2017上的文章,旨在解决联邦学习中安全聚合的问题。 安全聚合:多方参与者将信息传递给聚合者,聚合者除了知道这个信息的总和不能知道任何一个特定参与者的信息。 在这篇文章中,谷歌将用户手机作为联邦学习的客户端媒介,从而提出了联邦学习下
Earlier this year, Apple hosted the Privacy-Preserving Machine Learning (PPML) workshop. This virtual event brought Apple and members of the academic research communities together to discuss the state of the art in the field of privacy-preserving machine learning through a series of talks and disc...
Main idea. To tackle the above challenges, we propose a scheme named privacy-preserving machine learning under multiple keys (PMLM) to solve this problem. Since the secure multi-party computation (SMC) only supports the computation on the data encrypted under thesame public keyand the efficiency...
New and efficient protocols are provided for privacy-preserving machine learning training (e.g., for linear regression, logistic regression and neural network using the stochastic gradient descent method). A protocols can use the two-server model, where data owners distribute their private data among...
Training supervised machine learning models like deep learning requires high-quality labelled datasets that contain enough samples from various categories